@inproceedings{sivasankaran-etal-2018-phone,
title = "Phone Merging For Code-Switched Speech Recognition",
author = "Sivasankaran, Sunit and
Srivastava, Brij Mohan Lal and
Sitaram, Sunayana and
Bali, Kalika and
Choudhury, Monojit",
editor = "Aguilar, Gustavo and
AlGhamdi, Fahad and
Soto, Victor and
Solorio, Thamar and
Diab, Mona and
Hirschberg, Julia",
booktitle = "Proceedings of the Third Workshop on Computational Approaches to Linguistic Code-Switching",
month = jul,
year = "2018",
address = "Melbourne, Australia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W18-3202",
doi = "10.18653/v1/W18-3202",
pages = "11--19",
abstract = "Speakers in multilingual communities often switch between or mix multiple languages in the same conversation. Automatic Speech Recognition (ASR) of code-switched speech faces many challenges including the influence of phones of different languages on each other. This paper shows evidence that phone sharing between languages improves the Acoustic Model performance for Hindi-English code-switched speech. We compare baseline system built with separate phones for Hindi and English with systems where the phones were manually merged based on linguistic knowledge. Encouraged by the improved ASR performance after manually merging the phones, we further investigate multiple data-driven methods to identify phones to be merged across the languages. We show detailed analysis of automatic phone merging in this language pair and the impact it has on individual phone accuracies and WER. Though the best performance gain of 1.2{\%} WER was observed with manually merged phones, we show experimentally that the manual phone merge is not optimal.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sivasankaran-etal-2018-phone">
<titleInfo>
<title>Phone Merging For Code-Switched Speech Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sunit</namePart>
<namePart type="family">Sivasankaran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Brij</namePart>
<namePart type="given">Mohan</namePart>
<namePart type="given">Lal</namePart>
<namePart type="family">Srivastava</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunayana</namePart>
<namePart type="family">Sitaram</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Monojit</namePart>
<namePart type="family">Choudhury</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Workshop on Computational Approaches to Linguistic Code-Switching</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gustavo</namePart>
<namePart type="family">Aguilar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fahad</namePart>
<namePart type="family">AlGhamdi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Victor</namePart>
<namePart type="family">Soto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thamar</namePart>
<namePart type="family">Solorio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mona</namePart>
<namePart type="family">Diab</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Julia</namePart>
<namePart type="family">Hirschberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Melbourne, Australia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Speakers in multilingual communities often switch between or mix multiple languages in the same conversation. Automatic Speech Recognition (ASR) of code-switched speech faces many challenges including the influence of phones of different languages on each other. This paper shows evidence that phone sharing between languages improves the Acoustic Model performance for Hindi-English code-switched speech. We compare baseline system built with separate phones for Hindi and English with systems where the phones were manually merged based on linguistic knowledge. Encouraged by the improved ASR performance after manually merging the phones, we further investigate multiple data-driven methods to identify phones to be merged across the languages. We show detailed analysis of automatic phone merging in this language pair and the impact it has on individual phone accuracies and WER. Though the best performance gain of 1.2% WER was observed with manually merged phones, we show experimentally that the manual phone merge is not optimal.</abstract>
<identifier type="citekey">sivasankaran-etal-2018-phone</identifier>
<identifier type="doi">10.18653/v1/W18-3202</identifier>
<location>
<url>https://aclanthology.org/W18-3202</url>
</location>
<part>
<date>2018-07</date>
<extent unit="page">
<start>11</start>
<end>19</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Phone Merging For Code-Switched Speech Recognition
%A Sivasankaran, Sunit
%A Srivastava, Brij Mohan Lal
%A Sitaram, Sunayana
%A Bali, Kalika
%A Choudhury, Monojit
%Y Aguilar, Gustavo
%Y AlGhamdi, Fahad
%Y Soto, Victor
%Y Solorio, Thamar
%Y Diab, Mona
%Y Hirschberg, Julia
%S Proceedings of the Third Workshop on Computational Approaches to Linguistic Code-Switching
%D 2018
%8 July
%I Association for Computational Linguistics
%C Melbourne, Australia
%F sivasankaran-etal-2018-phone
%X Speakers in multilingual communities often switch between or mix multiple languages in the same conversation. Automatic Speech Recognition (ASR) of code-switched speech faces many challenges including the influence of phones of different languages on each other. This paper shows evidence that phone sharing between languages improves the Acoustic Model performance for Hindi-English code-switched speech. We compare baseline system built with separate phones for Hindi and English with systems where the phones were manually merged based on linguistic knowledge. Encouraged by the improved ASR performance after manually merging the phones, we further investigate multiple data-driven methods to identify phones to be merged across the languages. We show detailed analysis of automatic phone merging in this language pair and the impact it has on individual phone accuracies and WER. Though the best performance gain of 1.2% WER was observed with manually merged phones, we show experimentally that the manual phone merge is not optimal.
%R 10.18653/v1/W18-3202
%U https://aclanthology.org/W18-3202
%U https://doi.org/10.18653/v1/W18-3202
%P 11-19
Markdown (Informal)
[Phone Merging For Code-Switched Speech Recognition](https://aclanthology.org/W18-3202) (Sivasankaran et al., ACL 2018)
ACL
- Sunit Sivasankaran, Brij Mohan Lal Srivastava, Sunayana Sitaram, Kalika Bali, and Monojit Choudhury. 2018. Phone Merging For Code-Switched Speech Recognition. In Proceedings of the Third Workshop on Computational Approaches to Linguistic Code-Switching, pages 11–19, Melbourne, Australia. Association for Computational Linguistics.